# Claude Fable 5 vs GPT-5.1

As of Oct 15, 2026, Claude Fable 5 leads GPT-5.1 in 6 of 7 shared categories: General LLM, Reasoning, Coding › Web dev, Long context, Factuality, and Abstraction (ARC).

Claude Fable 5: $20 per 1M blended tokens.

GPT-5.1: $3.4375000000000004 per 1M blended tokens.

Claude Fable 5: closed weights.

GPT-5.1: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, Claude Fable 5 leads GPT-5.1 in General LLM at #3 against #60.
- Which to pick, Reasoning: As of Oct 15, 2026, Claude Fable 5 leads GPT-5.1 in Reasoning at #3 against #62.
- Which to pick, Science: As of Oct 15, 2026, GPT-5.1 leads Claude Fable 5 in Science at #48 against #56.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, Claude Fable 5 leads GPT-5.1 in Coding › Web dev at #19 against #82.
- Which to pick, Long context: As of Oct 15, 2026, Claude Fable 5 leads GPT-5.1 in Long context at #3 against #66.
- Which to pick, Factuality: As of Oct 15, 2026, Claude Fable 5 leads GPT-5.1 in Factuality at #7 against #42.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, Claude Fable 5 leads GPT-5.1 in Abstraction (ARC) at #1 against #31.

As of Oct 15, 2026, Claude Fable 5 is near state of the art, rank #3 in General LLM (since Oct 15, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).

As of Oct 15, 2026, GPT-5.1 is ranked #18 in Math (since Oct 15, 2026; sources Humanity's Last Exam; methodology v1.0).